vove
Follow
Starred repositories
Easily train a good VC model with voice data <= 10 mins!
Implementation of "DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation"
Interact with your documents using the power of GPT, 100% privately, no data leaks
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.
PhoWhisper: Automatic Speech Recognition for Vietnamese (2024)
Demo using PhoWhisper models of VinAI built with Transformers.js + Next.js
High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
A Vietnamese Voice Cloning Text-to-Speech Model ✨
A base Flutter project with MVVM architecture and Riverpod state management.
Convert any PDF into a podcast episode!
Convert any PDF into a podcast episode!
The Prometheus monitoring system and time series database.
A lightning-fast search API that fits effortlessly into your apps, websites, and workflow
From RAG chatbots to code assistants to complex agentic pipelines and beyond, build LLM systems that run better, faster, and cheaper with tracing, evaluations, and dashboards.
🎥 Make videos programmatically with React
✨ Local and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
Bypass Messenger SSL pinning on Android devices.
记录抖音热榜、明星榜、直播榜、音乐榜和品牌榜，每小时更新，按天归档。
Robust Speech Recognition via Large-Scale Weak Supervision
强大的 Frida 重打包工具，用于 iOS 和 Android。轻松修改 Frida 特征，增强隐蔽性，绕过检测。简化逆向工程和安全测试。Powerful Frida repackaging tool for iOS and Android. Easily modify Frida servers to enhance stealth and bypass detection. Strea…
